Adaptative Learning

8/3/2019 Adaptative Learning

1/35

1

Adaptive Learning Systems

Associate Professor KinshukInformation Systems Department

Massey University, Private Bag 11-222

Palmerston North, New Zealand

Tel: +64 6 350 5799 Ext 2090

Fax: +64 6 350 5725Email: [email protected]

URL: http://fims-www.massey.ac.nz/~kinshuk/


2/35

2

Introduction Adaptive learning systems with particular

focus on cognitive skills

Accommodation of both the instuctionand construction of knowledge

Design based on informed educational

methodologies


3/35

3

What exactly we mean by

Adaptivity

in

Adaptive Learning Systems?


4/35

4

Intelligence/adaptivity

Increased user efficiency, effectiveness

and satisfaction

by

Improved correspondence betweenlearner, goal and system characteristics


5/35

5

Need of

Intelligence/adaptivity

Users generally work on their ownwithout external support.

System is used by variety of users fromall over the world.

Customised system behaviour reducesmeta-learning overhead for the userand allows focus on completion ofactual task.


6/35

6

Adaptable SystemsSystems that allow the user to

change certain systemparameters and adapt the

system behaviour accordingly.

Adaptive Systems

Systems that adapt to the usersautomatically based on systemsassumptions about user needs.


7/35

7


8/35

8

How does adaptivity work?

System monitors users action patternswith various components of systemsinterface.

Some systems support the user in thelearning phase by introducing them tosystem operation.

Some systems draw users attention tounfamiliar tools.

User errors are primary candidate for

automatic adaptation.


9/35

9

Levels of adaptation

Simple: hard-wired

Self-regulating: monitors the effects of

adaptation and changes behaviouraccordingly

Self-mediating: Monitors the effects ofadaptation on model before putting into

practice

Self-modifying: Capable of chagingrepresentations by reasoning about the

interactions


10/35

10

Problems in adaptationUser is observed by the system, actions

are recorded, giving rise to data andprivacy protection issues.

Social monitoring becomes possibility.

User feels being controlled by the system.

User is exposed to adaptation conceptfavoured by the designer of the system.

User may be distracted from the task bysudden automatic modifications.


11/35

11

Recommendation for adaptive systems

Means for user to (de)activate or limitadaptation procedure

Offering adaptation in the form ofproposal

User may define specific parameters usedin adaptation

Giving user information about effects ofadaptation hence preventing surprises

Editable user model


12/35

12

Domain competence

And

computers


13/35

13

Constituents of

Domain

Competence

Know-whyKnow-how

Know-how-not Know-why-notKnow-when

Know-when-not

Know-what

logical processes

Know-about

Easier tolearn frommistakes

An example of theknow-howaspectofknow-when isthe temporalcontext required foran appropriate

sequence ofoperation

An example of theknow-whyaspectofknow-when isthe environmentaland behaviouralcontexts required

for making adecision

Action orientedand experiential

Reflection oriented andabstract

Difficult tolearn frommistakes

Trial and error

Context oriented and bothexperiential and abstract

Awareness oriented


14/35

14

Constituents of

Domain

Competence

Know-how

It has an operational orientation.

It is mainly action-driven and hence pre-

dominantly experiential. It is difficult to inherit it from someone

elses experience.

Know-how-not

Learning by mistakes.

Examples : Computer simulation and virtual

reality


15/35

15

Constituents of

Domain

Competence

Know-why

It has a causal orientation.

It is mainly reflection-driven and therefore

based on abstraction. It can be inherited from someone elses line

of reasoning.

Know-why-not Logical processes.

Needs deeper reflection.


16/35

16

Constituents of

Domain

Competence

Know-when (and -where)

It has a contextual orientation.

It provides the temporal and spatial contextfor both the know-how and know-why. It is

thus both action and/or reflection driven.


17/35

17

Constituents of

Domain

Competence

Know-about

It has an awareness orientation.

It includes above three types of knowledge interms ofknow-what.

It also contains information about the

environmental context of this knowledge.


18/35

18

Ideally, an instructional system, designed for novice

users, teach all knowledge constituents.

But, know-why is difficult to handle mainly for two

reasons:1. It needs natural language interaction.

2. It needs use of metaphors, which are difficult to

understand for a novice user.

Know-how, on the other hand, is operational, and

can be conveyed to the user more easily, even with

symbolic representations.

Instruction in knowledge context


19/35

19

Traditional hypermedia based ITSs approach, in

general, has been to teach the know-why aspect of

knowledge with the help of explanations.

The links provide stimulus to the user to know

more about a particular topic.

System works more as a friendly librarian and

learning depends on the initiative of a student.

Instruction in knowledge context


20/35

20

Theoretical framework bestsuitable for facilitation of

cognitive skills?

Cognitive ApprenticeFramework


21/35

21

Cognitive apprenticeship framework

Modelling: Learners study the task patternof experts to develop own cognitive model

Coaching: Learners solve tasks byconsulting a tutorial component of theenvironment

Fading: Tutorial activity is graduallyreduced in line with learners improvingperformance and problem solvingcompetence


22/35

22

Phases of Cognitive apprenticeship

1. World knowledge (initial requirement)

2. Observation of interactions among mastersand peers

3. Assisting in completion of tasks done bymaster

4. Trying out on own by imitating


23/35

23


5. Getting feedback from master

6. Getting advise for new things on the basisof results of imitation, comparing givensolution with alternatives

7. Reflection by student, resulting frommasters advice


24/35

24


8. Repetition of process from 2 to 7

Fading out guidance and feedback

Active participation, exploration andinnovation come in

9. Assessment of generalisation of the tasks

and concepts learnt during repetitionprocess


25/35

25

Example system

Cognitive apprenticeship based learningenvironment (CABLE)


26/35

26

Environment should facilitate:

acquisition of basic domain knowledge;

application of the basic domain knowledgein non-contextual and contextual scenariosto get skills of the discipline; and

generalisation of the domain knowledge toget competence of applying it in real worldsituations.

C

ABLE

objectives


27/35

27

C

ABLE

architectureObservation - for acquisition of concepts

Simple imitation - skills acquisition through

articulation of conceptsAdvanced imitation - generalisation and

abstraction of already acquired conceptsand for acquisition of skills of applying

concepts in different contexts


28/35

28

C

ABLE

architectureContextual observation - deeper learning

after imitation process results into theidentification of gaps in learners current

understanding of the domain knowledge

Interpretation of real life problems - foracquiring competence in such narrative

problems as encountered in real lifesituations


29/35

29

C

ABLE

architectureMastery in skills - for repetitive training

Assessment - for measurement of overall

progress


30/35

30

CABLETeacher generated

contextual problems

for generalised

learning & testing

Teacher generated

contextual problems for

strongly situated

learning & testing

System generatedproblems - random

selection of variables

Teacher generated richnarrative problems with model

answers to simulate real life

conditions

Descriptive text,illustrations and

solved examples

Use offine-grained

interfaces

Fine-graineddynamic

feedback

Why ? explanationfor the system

recommended solution

What did I do ?diagnostic

feedback

Tools of the Trade

Assessment

Intelligent Tutoring Tools

Listen/ Observe

Domains

concepts and

their purpose

Interactive Learning

Rehearsing/repairing

misconceptions and

missing concepts

Testing

Abstract

or

Single context

Testing

Multiple contexts

and/or

Rich narrative

Extending

Greater complexity

Building skills in

the use of tools

Learning by syntactic mapping ofinterface

objectsis possible

Ensures generalisation and far transfer of

knowledge

Instruction as the

main source


31/35

31

A network of inter-related variables where the

whole network remains constant.

Example, partial network of 7 out of a total of 14variables in marginal costing.

Intelligent Tutoring Tools Structure


32/35

32

Marginal costing relationships

R

VT CT

VU

Q

CU

R = VT + CTR = Q * P

P

CT = R - VTCT = Q * CU

Q = VT / VU

Q = CT / CUQ = R / P

CU = CT / Q

CU = P - VU

VU = VT / QVU = P - CU

VT = R - CTVT = Q * VU

P = R / Q

P =VU + CU


33/35

33

Structure of an ITT

Inference Engine

Context basedlink to textualdescription

User Interfacemodule

FileManagement

Input (student answer, position)Feedback

(four levels)

Knowledge Base1. Variables2. Relationships3. Tolerances

Modes

- Student

- Lecturer

- Administrator

RandomQuestionGenerator

DynamicMessaging

System

Tutoring

Module

Expert Model1. Correct values

2. Derivation procedure(Local expert model)

Student Model1. Student input2. Value status (filled or blank)3. Derivation procedure4. Interface preferences

Add-ons1. Calculator2. Table Interface3. Formula Interface

}Applicationspecific

MarkerLecturers model answer to

any lecturer generatednarrative questions

(Remote Expert Model)


34/35

34

Tutoring Strategy of an ITT

Introduction of complexity in phasedmanner

Corrective, elaborative and evaluativeaspects of student model are used fortutoring.

Learning process is broken down to verysmall steps through suitable interfaces.

Road to London paradigm is adopted toeliminate the need for diagnostic, predictiveand strategic aspects.


35/35

35

CABLE Demo

Future work on mentalprocess modelling

Adaptative Learning

Documents

Transcript of Adaptative Learning